From 1b6b8ce2ac372ea1f2065b89228ede105eb68dc5 Mon Sep 17 00:00:00 2001 From: Yu Zhao Date: Thu, 9 Apr 2009 14:57:39 +0800 Subject: PCI: only save/restore existent registers in the PCIe capability PCIe 1.1 base neither requires the endpoint to implement the entire PCIe capability structure nor specifies default values of registers that are not implemented by the device. So we only save and restore registers that must be implemented by different device types if the device PCIe capability version is 1. PCIe 1.1 Capability Structure Expansion ECN and PCIe 2.0 requires all registers in the PCIe capability to be either implemented or hardwired to 0. Their PCIe capability version is 2. Signed-off-by: Yu Zhao Signed-off-by: Jesse Barnes --- include/linux/pci_regs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/pci_regs.h b/include/linux/pci_regs.h index e4d08c1b2e0b..616bf8b3c8b5 100644 --- a/include/linux/pci_regs.h +++ b/include/linux/pci_regs.h @@ -376,6 +376,7 @@ #define PCI_EXP_TYPE_DOWNSTREAM 0x6 /* Downstream Port */ #define PCI_EXP_TYPE_PCI_BRIDGE 0x7 /* PCI/PCI-X Bridge */ #define PCI_EXP_TYPE_RC_END 0x9 /* Root Complex Integrated Endpoint */ +#define PCI_EXP_TYPE_RC_EC 0x10 /* Root Complex Event Collector */ #define PCI_EXP_FLAGS_SLOT 0x0100 /* Slot implemented */ #define PCI_EXP_FLAGS_IRQ 0x3e00 /* Interrupt message number */ #define PCI_EXP_DEVCAP 4 /* Device capabilities */ -- cgit v1.2.3 From 71951b64a5a87c09eb6fde59ce51aaab2fdaeab2 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Fri, 24 Apr 2009 16:58:41 +0200 Subject: netfilter: nf_ct_dccp: add missing role attributes for DCCP This patch adds missing role attribute to the DCCP type, otherwise the creation of entries is not of any use. The attribute added is CTA_PROTOINFO_DCCP_ROLE which contains the role of the conntrack original tuple. Signed-off-by: Pablo Neira Ayuso Signed-off-by: Patrick McHardy --- include/linux/netfilter/nfnetlink_conntrack.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/netfilter/nfnetlink_conntrack.h b/include/linux/netfilter/nfnetlink_conntrack.h index 29fe9ea1d346..1a865e48b8eb 100644 --- a/include/linux/netfilter/nfnetlink_conntrack.h +++ b/include/linux/netfilter/nfnetlink_conntrack.h @@ -100,6 +100,7 @@ enum ctattr_protoinfo_tcp { enum ctattr_protoinfo_dccp { CTA_PROTOINFO_DCCP_UNSPEC, CTA_PROTOINFO_DCCP_STATE, + CTA_PROTOINFO_DCCP_ROLE, __CTA_PROTOINFO_DCCP_MAX, }; #define CTA_PROTOINFO_DCCP_MAX (__CTA_PROTOINFO_DCCP_MAX - 1) -- cgit v1.2.3 From c80d471a476b6d6fe0bc1fd25293c24c66b7aaaf Mon Sep 17 00:00:00 2001 From: Tim Abbott Date: Sat, 25 Apr 2009 22:10:56 -0400 Subject: Add new HEAD_TEXT_SECTION macro. This patch is preparation for replacing all uses of ".head.text" or ".text.head" in the kernel with macros, so that the section name can later be changed without having to touch a lot of the kernel. Since some linker scripts do more complex things than referencing HEAD_TEXT, we add a HEAD_TEXT_SECTION macro that just contains the actual name. I've defined HEAD_TEXT_SECTION in a new header, include/linux/section-names.h, so that this section name only needs to appear in one place. I anticipate creating similar macro structures for a number of other section names. The long-term goal here is to be able to change the kernel's magic section names to those that are compatible with -ffunction-sections -fdata-sections. This requires renaming all magic sections with names of the form ".text.foo". Signed-off-by: Tim Abbott Signed-off-by: Linus Torvalds --- include/linux/init.h | 4 +++- include/linux/section-names.h | 6 ++++++ 2 files changed, 9 insertions(+), 1 deletion(-) create mode 100644 include/linux/section-names.h (limited to 'include/linux') diff --git a/include/linux/init.h b/include/linux/init.h index f121a7a10c3d..20a1334e34e9 100644 --- a/include/linux/init.h +++ b/include/linux/init.h @@ -2,6 +2,8 @@ #define _LINUX_INIT_H #include +#include +#include /* These macros are used to mark some functions or * initialized data (doesn't apply to uninitialized data) @@ -107,7 +109,7 @@ #define __memexitconst __section(.memexit.rodata) /* For assembly routines */ -#define __HEAD .section ".head.text","ax" +#define __HEAD .section __stringify(HEAD_TEXT_SECTION),"ax" #define __INIT .section ".init.text","ax" #define __FINIT .previous diff --git a/include/linux/section-names.h b/include/linux/section-names.h new file mode 100644 index 000000000000..c956f4eb2adf --- /dev/null +++ b/include/linux/section-names.h @@ -0,0 +1,6 @@ +#ifndef __LINUX_SECTION_NAMES_H +#define __LINUX_SECTION_NAMES_H + +#define HEAD_TEXT_SECTION .head.text + +#endif /* !__LINUX_SECTION_NAMES_H */ -- cgit v1.2.3 From c759a6b4e1cae6aff71f58c9c85404ebcd81b6e0 Mon Sep 17 00:00:00 2001 From: Adrian Bunk Date: Mon, 27 Apr 2009 02:36:20 -0700 Subject: net: Fix LL_MAX_HEADER for CONFIG_TR_MODULE Unless I miss anything this should fix a bug. Signed-off-by: Adrian Bunk Signed-off-by: David S. Miller --- include/linux/netdevice.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 2e7783f4a755..453be9a674c0 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -104,7 +104,7 @@ struct wireless_dev; # else # define LL_MAX_HEADER 96 # endif -#elif defined(CONFIG_TR) +#elif defined(CONFIG_TR) || defined(CONFIG_TR_MODULE) # define LL_MAX_HEADER 48 #else # define LL_MAX_HEADER 32 -- cgit v1.2.3 From 37b607c5ac3b7c92a6a3624bb29f1cdcdcf7044a Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Mon, 27 Apr 2009 05:45:54 -0700 Subject: net: Fix typo in net_device_ops description. Signed-off-by: Mike Rapoport Signed-off-by: David S. Miller --- include/linux/netdevice.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 453be9a674c0..5a96a1a406e9 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -500,7 +500,7 @@ struct netdev_queue { * * int (*ndo_set_mac_address)(struct net_device *dev, void *addr); * This function is called when the Media Access Control address - * needs to be changed. If not this interface is not defined, the + * needs to be changed. If this interface is not defined, the * mac address can not be changed. * * int (*ndo_validate_addr)(struct net_device *dev); -- cgit v1.2.3 From 27b1833279995e7c290a40cac4ef36ccea7e9283 Mon Sep 17 00:00:00 2001 From: Tim Abbott Date: Mon, 27 Apr 2009 14:02:27 -0400 Subject: Remove unused support code for refok sections. The old refok sections .text.init.refok .data.init.refok .exit.text.refok have been deprecated since commit 312b1485fb509c9bc32eda28ad29537896658cb8. After the other patches in this patch series nothing is put in these sections, so clean things up by eliminating all the remaining references to them. Signed-off-by: Tim Abbott Acked-by: Sam Ravnborg Signed-off-by: Linus Torvalds --- include/linux/init.h | 8 -------- 1 file changed, 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/init.h b/include/linux/init.h index 20a1334e34e9..0e06c176f185 100644 --- a/include/linux/init.h +++ b/include/linux/init.h @@ -62,14 +62,6 @@ #define __refdata __section(.ref.data) #define __refconst __section(.ref.rodata) -/* backward compatibility note - * A few places hardcode the old section names: - * .text.init.refok - * .data.init.refok - * .exit.text.refok - * They should be converted to use the defines from this file - */ - /* compatibility defines */ #define __init_refok __ref #define __initdata_refok __refdata -- cgit v1.2.3 From bf368e4e70cd4e0f880923c44e95a4273d725ab4 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 28 Apr 2009 02:24:21 -0700 Subject: net: Avoid extra wakeups of threads blocked in wait_for_packet() In 2.6.25 we added UDP mem accounting. This unfortunatly added a penalty when a frame is transmitted, since we have at TX completion time to call sock_wfree() to perform necessary memory accounting. This calls sock_def_write_space() and utimately scheduler if any thread is waiting on the socket. Thread(s) waiting for an incoming frame was scheduled, then had to sleep again as event was meaningless. (All threads waiting on a socket are using same sk_sleep anchor) This adds lot of extra wakeups and increases latencies, as noted by Christoph Lameter, and slows down softirq handler. Reference : http://marc.info/?l=linux-netdev&m=124060437012283&w=2 Fortunatly, Davide Libenzi recently added concept of keyed wakeups into kernel, and particularly for sockets (see commit 37e5540b3c9d838eb20f2ca8ea2eb8072271e403 epoll keyed wakeups: make sockets use keyed wakeups) Davide goal was to optimize epoll, but this new wakeup infrastructure can help non epoll users as well, if they care to setup an appropriate handler. This patch introduces new DEFINE_WAIT_FUNC() helper and uses it in wait_for_packet(), so that only relevant event can wakeup a thread blocked in this function. Trace of function calls from bnx2 TX completion bnx2_poll_work() is : __kfree_skb() skb_release_head_state() sock_wfree() sock_def_write_space() __wake_up_sync_key() __wake_up_common() receiver_wake_function() : Stops here since thread is waiting for an INPUT Reported-by: Christoph Lameter Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/wait.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/wait.h b/include/linux/wait.h index 5d631c17eaee..bc024632f365 100644 --- a/include/linux/wait.h +++ b/include/linux/wait.h @@ -440,13 +440,15 @@ void abort_exclusive_wait(wait_queue_head_t *q, wait_queue_t *wait, int autoremove_wake_function(wait_queue_t *wait, unsigned mode, int sync, void *key); int wake_bit_function(wait_queue_t *wait, unsigned mode, int sync, void *key); -#define DEFINE_WAIT(name) \ +#define DEFINE_WAIT_FUNC(name, function) \ wait_queue_t name = { \ .private = current, \ - .func = autoremove_wake_function, \ + .func = function, \ .task_list = LIST_HEAD_INIT((name).task_list), \ } +#define DEFINE_WAIT(name) DEFINE_WAIT_FUNC(name, autoremove_wake_function) + #define DEFINE_WAIT_BIT(name, word, bit) \ struct wait_bit_queue name = { \ .key = __WAIT_BIT_KEY_INITIALIZER(word, bit), \ -- cgit v1.2.3 From 6916d97f6e25cc66a32d6e9a16419067d843b14f Mon Sep 17 00:00:00 2001 From: Henrik Rydberg Date: Mon, 27 Apr 2009 11:52:43 -0700 Subject: Input: bcm5974 - add quad-finger tapping The integrated button on the new unibody Macbooks presents a need to report explicit four-finger actions. Evidently, the finger pressing the button is also touching the trackpad, so in order to fully support three-finger actions, the driver must be able to report four-finger actions. This patch adds a new button, BTN_TOOL_QUADTAP, which achieves this. Signed-off-by: Henrik Rydberg Signed-off-by: Dmitry Torokhov --- include/linux/input.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/input.h b/include/linux/input.h index 6b28048fc568..32cb825939be 100644 --- a/include/linux/input.h +++ b/include/linux/input.h @@ -445,6 +445,7 @@ struct input_absinfo { #define BTN_STYLUS2 0x14c #define BTN_TOOL_DOUBLETAP 0x14d #define BTN_TOOL_TRIPLETAP 0x14e +#define BTN_TOOL_QUADTAP 0x14f /* Four fingers on trackpad */ #define BTN_WHEEL 0x150 #define BTN_GEAR_DOWN 0x150 -- cgit v1.2.3 From 5e5ee686e3c0f8a3cbe9b75c2690326bf91af10d Mon Sep 17 00:00:00 2001 From: Henrik Rydberg Date: Tue, 28 Apr 2009 07:47:33 -0700 Subject: Input: add detailed multi-touch finger data report protocol In order to utilize the full power of the new multi-touch devices, a way to report detailed finger data to user space is needed. This patch adds a multi-touch (MT) protocol which allows drivers to report details for an arbitrary number of fingers. The driver sends a SYN_MT_REPORT event via the input_mt_sync() function when a complete finger has been reported. In order to stay compatible with existing applications, the data reported in a finger packet must not be recognized as single-touch events. In addition, all finger data must bypass input filtering, since subsequent events of the same type refer to different fingers. A set of ABS_MT events with the desired properties are defined. The events are divided into categories, to allow for partial implementation. The minimum set consists of ABS_MT_TOUCH_MAJOR, ABS_MT_POSITION_X and ABS_MT_POSITION_Y, which allows for multiple fingers to be tracked. If the device supports it, the ABS_MT_WIDTH_MAJOR may be used to provide the size of the approaching finger. Anisotropy and direction may be specified with ABS_MT_TOUCH_MINOR, ABS_MT_WIDTH_MINOR and ABS_MT_ORIENTATION. Devices with more granular information may specify general shapes as blobs, i.e., as a sequence of rectangular shapes grouped together by a ABS_MT_BLOB_ID. Finally, the ABS_MT_TOOL_TYPE may be used to specify whether the touching tool is a finger or a pen. Signed-off-by: Henrik Rydberg Signed-off-by: Dmitry Torokhov --- include/linux/input.h | 23 +++++++++++++++++++++++ 1 file changed, 23 insertions(+) (limited to 'include/linux') diff --git a/include/linux/input.h b/include/linux/input.h index 32cb825939be..0e6ff5de3588 100644 --- a/include/linux/input.h +++ b/include/linux/input.h @@ -106,6 +106,7 @@ struct input_absinfo { #define SYN_REPORT 0 #define SYN_CONFIG 1 +#define SYN_MT_REPORT 2 /* * Keys and buttons @@ -645,6 +646,17 @@ struct input_absinfo { #define ABS_TOOL_WIDTH 0x1c #define ABS_VOLUME 0x20 #define ABS_MISC 0x28 + +#define ABS_MT_TOUCH_MAJOR 0x30 /* Major axis of touching ellipse */ +#define ABS_MT_TOUCH_MINOR 0x31 /* Minor axis (omit if circular) */ +#define ABS_MT_WIDTH_MAJOR 0x32 /* Major axis of approaching ellipse */ +#define ABS_MT_WIDTH_MINOR 0x33 /* Minor axis (omit if circular) */ +#define ABS_MT_ORIENTATION 0x34 /* Ellipse orientation */ +#define ABS_MT_POSITION_X 0x35 /* Center X ellipse position */ +#define ABS_MT_POSITION_Y 0x36 /* Center Y ellipse position */ +#define ABS_MT_TOOL_TYPE 0x37 /* Type of touching device */ +#define ABS_MT_BLOB_ID 0x38 /* Group a set of packets as a blob */ + #define ABS_MAX 0x3f #define ABS_CNT (ABS_MAX+1) @@ -743,6 +755,12 @@ struct input_absinfo { #define BUS_GSC 0x1A #define BUS_ATARI 0x1B +/* + * MT_TOOL types + */ +#define MT_TOOL_FINGER 0 +#define MT_TOOL_PEN 1 + /* * Values describing the status of a force-feedback effect */ @@ -1312,6 +1330,11 @@ static inline void input_sync(struct input_dev *dev) input_event(dev, EV_SYN, SYN_REPORT, 0); } +static inline void input_mt_sync(struct input_dev *dev) +{ + input_event(dev, EV_SYN, SYN_MT_REPORT, 0); +} + void input_set_capability(struct input_dev *dev, unsigned int type, unsigned int code); static inline void input_set_abs_params(struct input_dev *dev, int axis, int min, int max, int fuzz, int flat) -- cgit v1.2.3 From 9f6532519feab921856f41b30a2397ee25f4de49 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Fri, 3 Apr 2009 21:31:30 -0700 Subject: regulator: fix header file missing kernel-doc Add regulator header file missing kernel-doc: Warning(include/linux/regulator/driver.h:117): No description found for parameter 'set_mode' Signed-off-by: Randy Dunlap cc: Liam Girdwood cc: Mark Brown Signed-off-by: Liam Girdwood --- include/linux/regulator/driver.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/regulator/driver.h b/include/linux/regulator/driver.h index 4848d8dacd90..225f733e7533 100644 --- a/include/linux/regulator/driver.h +++ b/include/linux/regulator/driver.h @@ -50,6 +50,7 @@ enum regulator_status { * @set_current_limit: Configure a limit for a current-limited regulator. * @get_current_limit: Get the configured limit for a current-limited regulator. * + * @set_mode: Set the configured operating mode for the regulator. * @get_mode: Get the configured operating mode for the regulator. * @get_status: Return actual (not as-configured) status of regulator, as a * REGULATOR_STATUS value (or negative errno) -- cgit v1.2.3 From 942e4a2bd680c606af0211e64eb216be2e19bf61 Mon Sep 17 00:00:00 2001 From: Stephen Hemminger Date: Tue, 28 Apr 2009 22:36:33 -0700 Subject: netfilter: revised locking for x_tables The x_tables are organized with a table structure and a per-cpu copies of the counters and rules. On older kernels there was a reader/writer lock per table which was a performance bottleneck. In 2.6.30-rc, this was converted to use RCU and the counters/rules which solved the performance problems for do_table but made replacing rules much slower because of the necessary RCU grace period. This version uses a per-cpu set of spinlocks and counters to allow to table processing to proceed without the cache thrashing of a global reader lock and keeps the same performance for table updates. Signed-off-by: Stephen Hemminger Acked-by: Linus Torvalds Signed-off-by: David S. Miller --- include/linux/netfilter/x_tables.h | 73 +++++++++++++++++++++++++++++++++++--- 1 file changed, 68 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter/x_tables.h b/include/linux/netfilter/x_tables.h index 7b1a652066c0..1b2e43502ef7 100644 --- a/include/linux/netfilter/x_tables.h +++ b/include/linux/netfilter/x_tables.h @@ -354,9 +354,6 @@ struct xt_table /* What hooks you will enter on */ unsigned int valid_hooks; - /* Lock for the curtain */ - struct mutex lock; - /* Man behind the curtain... */ struct xt_table_info *private; @@ -434,8 +431,74 @@ extern void xt_proto_fini(struct net *net, u_int8_t af); extern struct xt_table_info *xt_alloc_table_info(unsigned int size); extern void xt_free_table_info(struct xt_table_info *info); -extern void xt_table_entry_swap_rcu(struct xt_table_info *old, - struct xt_table_info *new); + +/* + * Per-CPU spinlock associated with per-cpu table entries, and + * with a counter for the "reading" side that allows a recursive + * reader to avoid taking the lock and deadlocking. + * + * "reading" is used by ip/arp/ip6 tables rule processing which runs per-cpu. + * It needs to ensure that the rules are not being changed while the packet + * is being processed. In some cases, the read lock will be acquired + * twice on the same CPU; this is okay because of the count. + * + * "writing" is used when reading counters. + * During replace any readers that are using the old tables have to complete + * before freeing the old table. This is handled by the write locking + * necessary for reading the counters. + */ +struct xt_info_lock { + spinlock_t lock; + unsigned char readers; +}; +DECLARE_PER_CPU(struct xt_info_lock, xt_info_locks); + +/* + * Note: we need to ensure that preemption is disabled before acquiring + * the per-cpu-variable, so we do it as a two step process rather than + * using "spin_lock_bh()". + * + * We _also_ need to disable bottom half processing before updating our + * nesting count, to make sure that the only kind of re-entrancy is this + * code being called by itself: since the count+lock is not an atomic + * operation, we can allow no races. + * + * _Only_ that special combination of being per-cpu and never getting + * re-entered asynchronously means that the count is safe. + */ +static inline void xt_info_rdlock_bh(void) +{ + struct xt_info_lock *lock; + + local_bh_disable(); + lock = &__get_cpu_var(xt_info_locks); + if (!lock->readers++) + spin_lock(&lock->lock); +} + +static inline void xt_info_rdunlock_bh(void) +{ + struct xt_info_lock *lock = &__get_cpu_var(xt_info_locks); + + if (!--lock->readers) + spin_unlock(&lock->lock); + local_bh_enable(); +} + +/* + * The "writer" side needs to get exclusive access to the lock, + * regardless of readers. This must be called with bottom half + * processing (and thus also preemption) disabled. + */ +static inline void xt_info_wrlock(unsigned int cpu) +{ + spin_lock(&per_cpu(xt_info_locks, cpu).lock); +} + +static inline void xt_info_wrunlock(unsigned int cpu) +{ + spin_unlock(&per_cpu(xt_info_locks, cpu).lock); +} /* * This helper is performance critical and must be inlined -- cgit v1.2.3 From 96c16743973e8c1a7b9c655d10b7973408d6d1dd Mon Sep 17 00:00:00 2001 From: Borislav Petkov Date: Thu, 30 Apr 2009 18:24:34 +0200 Subject: ide-cd: fix REQ_QUIET tests in cdrom_decode_status Original patch (dfa4411cc3a690011cab90e9a536938795366cf9) was buggy. This is a more proper fix which introduces blk_rq_quiet() macro alleviating the need for dumb, too short caching variables. Thanks to Helge Deller and Bart for debugging this. Signed-off-by: Borislav Petkov Cc: Jens Axboe Cc: Sergei Shtylyov Reported-and-tested-by: Helge Deller Signed-off-by: Bartlomiej Zolnierkiewicz --- include/linux/blkdev.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index ba54c834a590..6f841fb1be30 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -598,6 +598,7 @@ enum { blk_failfast_transport(rq) || \ blk_failfast_driver(rq)) #define blk_rq_started(rq) ((rq)->cmd_flags & REQ_STARTED) +#define blk_rq_quiet(rq) ((rq)->cmd_flags & REQ_QUIET) #define blk_account_rq(rq) (blk_rq_started(rq) && (blk_fs_request(rq) || blk_discard_rq(rq))) -- cgit v1.2.3 From ae3abae64f177586be55b04a7fb7047a34b21a3e Mon Sep 17 00:00:00 2001 From: Daisuke Nishimura Date: Thu, 30 Apr 2009 15:08:19 -0700 Subject: memcg: fix mem_cgroup_shrink_usage() Current mem_cgroup_shrink_usage() has two problems. 1. It doesn't call mem_cgroup_out_of_memory and doesn't update last_oom_jiffies, so pagefault_out_of_memory invokes global OOM. 2. Considering hierarchy, shrinking has to be done from the mem_over_limit, not from the memcg which the page would be charged to. mem_cgroup_try_charge_swapin() does all of these things properly, so we use it and call cancel_charge_swapin when it succeeded. The name of "shrink_usage" is not appropriate for this behavior, so we change it too. Signed-off-by: Daisuke Nishimura Acked-by: KAMEZAWA Hiroyuki Cc: Li Zefan Cc: Paul Menage Cc: Dhaval Giani Cc: Daisuke Nishimura Cc: YAMAMOTO Takashi Cc: KOSAKI Motohiro Cc: David Rientjes Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index a9e3b76aa884..25b9ca93d232 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -56,7 +56,7 @@ extern void mem_cgroup_move_lists(struct page *page, enum lru_list from, enum lru_list to); extern void mem_cgroup_uncharge_page(struct page *page); extern void mem_cgroup_uncharge_cache_page(struct page *page); -extern int mem_cgroup_shrink_usage(struct page *page, +extern int mem_cgroup_shmem_charge_fallback(struct page *page, struct mm_struct *mm, gfp_t gfp_mask); extern unsigned long mem_cgroup_isolate_pages(unsigned long nr_to_scan, @@ -155,7 +155,7 @@ static inline void mem_cgroup_uncharge_cache_page(struct page *page) { } -static inline int mem_cgroup_shrink_usage(struct page *page, +static inline int mem_cgroup_shmem_charge_fallback(struct page *page, struct mm_struct *mm, gfp_t gfp_mask) { return 0; -- cgit v1.2.3 From 74641f584da8eccf30becfbb5507ab457187db22 Mon Sep 17 00:00:00 2001 From: Ivan Kokshaysky Date: Thu, 30 Apr 2009 15:08:49 -0700 Subject: alpha: binfmt_aout fix This fixes the problem introduced by commit 3bfacef412 (get rid of special-casing the /sbin/loader on alpha): osf/1 ecoff binary segfaults when binfmt_aout built as module. That happens because aout binary handler gets on the top of the binfmt list due to late registration, and kernel attempts to execute the binary without preparatory work that must be done by binfmt_loader. Fixed by changing the registration order of the default binfmt handlers using list_add_tail() and introducing insert_binfmt() function which places new handler on the top of the binfmt list. This might be generally useful for installing arch-specific frontends for default handlers or just for overriding them. Signed-off-by: Ivan Kokshaysky Cc: Al Viro Cc: Richard Henderson Signed-off-by: Linus Torvalds --- include/linux/binfmts.h | 14 +++++++++++++- 1 file changed, 13 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/binfmts.h b/include/linux/binfmts.h index 6638b8148de7..61ee18c1bdb4 100644 --- a/include/linux/binfmts.h +++ b/include/linux/binfmts.h @@ -82,7 +82,19 @@ struct linux_binfmt { int hasvdso; }; -extern int register_binfmt(struct linux_binfmt *); +extern int __register_binfmt(struct linux_binfmt *fmt, int insert); + +/* Registration of default binfmt handlers */ +static inline int register_binfmt(struct linux_binfmt *fmt) +{ + return __register_binfmt(fmt, 0); +} +/* Same as above, but adds a new binfmt at the top of the list */ +static inline int insert_binfmt(struct linux_binfmt *fmt) +{ + return __register_binfmt(fmt, 1); +} + extern void unregister_binfmt(struct linux_binfmt *); extern int prepare_binprm(struct linux_binprm *); -- cgit v1.2.3 From 0763ed2355198cdef2f6a2098e9d52eb1fe4365d Mon Sep 17 00:00:00 2001 From: Grant Likely Date: Thu, 30 Apr 2009 15:08:50 -0700 Subject: of: make of_(un)register_platform_driver common code Some drivers using of_register_platform_driver() wrapper break on sparc because the wrapper isn't in the header file. This patch moves it from Microblaze and PowerPC implementations and makes it common code. Fixes this sparc64 allmodconfig build error (at least): drivers/leds/leds-gpio.c: In function `gpio_led_init': drivers/leds/leds-gpio.c:295: error: implicit declaration of function `of_register_platform_driver' drivers/leds/leds-gpio.c: In function `gpio_led_exit': drivers/leds/leds-gpio.c:311: error: implicit declaration of function `of_unregister_platform_driver' Signed-off-by: Grant Likely Acked-by: David S. Miller Cc: Michal Simek Cc: Benjamin Herrenschmidt Cc: Stephen Rothwell Cc: Richard Purdie Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/of_platform.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/of_platform.h b/include/linux/of_platform.h index 3d327b67d7e2..908406651330 100644 --- a/include/linux/of_platform.h +++ b/include/linux/of_platform.h @@ -51,6 +51,16 @@ extern int of_register_driver(struct of_platform_driver *drv, struct bus_type *bus); extern void of_unregister_driver(struct of_platform_driver *drv); +/* Platform drivers register/unregister */ +static inline int of_register_platform_driver(struct of_platform_driver *drv) +{ + return of_register_driver(drv, &of_platform_bus_type); +} +static inline void of_unregister_platform_driver(struct of_platform_driver *drv) +{ + of_unregister_driver(drv); +} + #include extern struct of_device *of_find_device_by_node(struct device_node *np); -- cgit v1.2.3 From 00a62ce91e554198ef28234c91c36f850f5a3bc9 Mon Sep 17 00:00:00 2001 From: KOSAKI Motohiro Date: Thu, 30 Apr 2009 15:08:51 -0700 Subject: mm: fix Committed_AS underflow on large NR_CPUS environment The Committed_AS field can underflow in certain situations: > # while true; do cat /proc/meminfo | grep _AS; sleep 1; done | uniq -c > 1 Committed_AS: 18446744073709323392 kB > 11 Committed_AS: 18446744073709455488 kB > 6 Committed_AS: 35136 kB > 5 Committed_AS: 18446744073709454400 kB > 7 Committed_AS: 35904 kB > 3 Committed_AS: 18446744073709453248 kB > 2 Committed_AS: 34752 kB > 9 Committed_AS: 18446744073709453248 kB > 8 Committed_AS: 34752 kB > 3 Committed_AS: 18446744073709320960 kB > 7 Committed_AS: 18446744073709454080 kB > 3 Committed_AS: 18446744073709320960 kB > 5 Committed_AS: 18446744073709454080 kB > 6 Committed_AS: 18446744073709320960 kB Because NR_CPUS can be greater than 1000 and meminfo_proc_show() does not check for underflow. But NR_CPUS proportional isn't good calculation. In general, possibility of lock contention is proportional to the number of online cpus, not theorical maximum cpus (NR_CPUS). The current kernel has generic percpu-counter stuff. using it is right way. it makes code simplify and percpu_counter_read_positive() don't make underflow issue. Reported-by: Dave Hansen Signed-off-by: KOSAKI Motohiro Cc: Eric B Munson Cc: Mel Gorman Cc: Christoph Lameter Cc: [All kernel versions] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mman.h | 9 +++------ 1 file changed, 3 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mman.h b/include/linux/mman.h index 30d1073bac3b..9872d6ca58ae 100644 --- a/include/linux/mman.h +++ b/include/linux/mman.h @@ -12,21 +12,18 @@ #ifdef __KERNEL__ #include +#include #include extern int sysctl_overcommit_memory; extern int sysctl_overcommit_ratio; -extern atomic_long_t vm_committed_space; +extern struct percpu_counter vm_committed_as; -#ifdef CONFIG_SMP -extern void vm_acct_memory(long pages); -#else static inline void vm_acct_memory(long pages) { - atomic_long_add(pages, &vm_committed_space); + percpu_counter_add(&vm_committed_as, pages); } -#endif static inline void vm_unacct_memory(long pages) { -- cgit v1.2.3 From f75e6745aa3084124ae1434fd7629853bdaf6798 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Tue, 21 Apr 2009 17:18:20 -0400 Subject: SUNRPC: Fix the problem of EADDRNOTAVAIL syslog floods on reconnect See http://bugzilla.kernel.org/show_bug.cgi?id=13034 If the port gets into a TIME_WAIT state, then we cannot reconnect without binding to a new port. Tested-by: Petr Vandrovec Tested-by: Jean Delvare Signed-off-by: Trond Myklebust Signed-off-by: Linus Torvalds --- include/linux/sunrpc/xprt.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index 1758d9f5b5c3..08afe43118f4 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -261,6 +261,7 @@ void xprt_conditional_disconnect(struct rpc_xprt *xprt, unsigned int cookie); #define XPRT_BINDING (5) #define XPRT_CLOSING (6) #define XPRT_CONNECTION_ABORT (7) +#define XPRT_CONNECTION_CLOSE (8) static inline void xprt_set_connected(struct rpc_xprt *xprt) { -- cgit v1.2.3